CN103677642A - Touch screen terminal and method and system for identifying hand gestures of touch screen terminal - Google Patents

Touch screen terminal and method and system for identifying hand gestures of touch screen terminal Download PDF

Info

Publication number
CN103677642A
CN103677642A CN201310700794.8A CN201310700794A CN103677642A CN 103677642 A CN103677642 A CN 103677642A CN 201310700794 A CN201310700794 A CN 201310700794A CN 103677642 A CN103677642 A CN 103677642A
Authority
CN
China
Prior art keywords
sequence
direction vector
touch screen
module
gesture
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201310700794.8A
Other languages
Chinese (zh)
Inventor
周旭武
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Goodix Technology Co Ltd
Original Assignee
Shenzhen Huiding Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Huiding Technology Co Ltd filed Critical Shenzhen Huiding Technology Co Ltd
Priority to CN201310700794.8A priority Critical patent/CN103677642A/en
Publication of CN103677642A publication Critical patent/CN103677642A/en
Priority to PCT/CN2014/084146 priority patent/WO2015090075A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
    • G06F2203/041—Indexing scheme relating to G06F3/041 - G06F3/045
    • G06F2203/04104—Multi-touch detection in digitiser, i.e. details about the simultaneous detection of a plurality of touching locations, e.g. multiple fingers or pen and finger
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
    • G06F2203/048—Indexing scheme relating to G06F3/048
    • G06F2203/04808—Several contacts: gestures triggering a specific function, e.g. scrolling, zooming, right-click, when the user establishes several contacts with the surface simultaneously; e.g. using several fingers or a combination of fingers and pen
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
    • G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means

Abstract

The invention belongs to the field of man-computer interaction of touch screen terminals, and provides a touch screen terminal and a method and system for identifying hand gestures of the touch screen terminal. According to the method and system, a series of feature points of the hand gestures are colleted through a touch screen, direction vector encoding is carried out on the feature points, the encoded result is matched with a reference template, so that symbols corresponding to the hand gestures are obtained, and symbols formed by touch screen sliding hand gestures of a user can be effectively identified. Compared with the prior art, the identification method is simple to achieve, the user can conveniently operate the touch screen terminal, supporting of a camera is not needed, cost can be lowered, the method can not be affected by surrounding light or the moving state of the touch screen terminal, and the identification rate is high.

Description

A kind of touch screen terminal and gesture identification method thereof, system
Technical field
The invention belongs to the field of human-computer interaction of touch screen terminal, relate in particular to a kind of touch screen terminal and gesture identification method thereof, system.
Background technology
In field of human-computer interaction, gesture refers to the set of the information with specific meanings that the combination of the mankind by finger or the different gestures of palm forms.In current touch screen terminal, can utilize gesture to operate, so that the user experience of application program obtains larger lifting.
In prior art, touch screen terminal is to extract images of gestures based on optical means, by the consecutive image gathering is carried out to image processing, extracts relevant characteristic, and then utilizes characteristic to identify gesture.But this recognition method algorithm is complicated, need to coordinate camera to use, and realizes cost high, and when touch screen terminal is in the poor environment of light or in mobile status, discrimination is low.
Summary of the invention
First technical matters to be solved by this invention is to provide a kind of gesture identification method of touch screen terminal, be intended to solve existing touch screen terminal and realize gesture identification based on optical means, it is embodied as high, and under the poor environment of light or mobile status the low problem of discrimination.
The present invention is achieved in that a kind of gesture identification method of touch screen terminal, said method comprising the steps of:
By touch-screen, obtain the coordinate point sequence of gesture, and coordinate point sequence is carried out to filtering processing;
Extract minutiae in described coordinate point sequence from filtering is processed;
To described unique point travel direction vector coding, obtain direction vector sequence;
Described direction vector sequence is mated with reference template, and to identify the symbol corresponding with described gesture, described reference template has characterized the corresponding relation between symbol and direction vector sequence.
Second technical matters to be solved by this invention is to provide a kind of gesture recognition system of touch screen terminal, and described system comprises:
Pretreatment module, for obtain the coordinate point sequence of gesture by touch-screen, and carries out filtering processing to described coordinate point sequence;
Characteristic extracting module, for the described coordinate point sequence extract minutiae from described pretreatment module filtering is processed;
Direction vector coding module, the described unique point travel direction vector coding for described characteristic extracting module is extracted, obtains direction vector sequence;
Matching module, mates with reference template for the described direction vector sequence that described direction vector coding module is obtained, and to identify the symbol corresponding with gesture, described reference template has characterized the corresponding relation between symbol and direction vector sequence.
The 3rd technical matters to be solved by this invention is to provide a kind of touch screen terminal, comprises touch-screen, and described touch screen terminal also comprises the gesture recognition system of touch screen terminal, and described system is the gesture recognition system of touch screen terminal as above.
Gesture identification method and the system of the touch screen terminal that the present invention proposes are to gather the series of features point in gesture by touch-screen, by to unique point travel direction vector coding, and coding result is mated with reference template, thereby obtain the symbol corresponding with gesture, can effectively identify the formed symbol of user's gesture slip touch-screen.With respect to prior art, this recognition method realizes simple, user-friendly, and without camera support, can reduce and realize cost, and is not subject to the impact of ambient light or touch screen terminal mobile status, and discrimination is high.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the gesture identification method of touch screen terminal provided by the invention;
Fig. 2 is the detail flowchart of the step of extract minutiae of the present invention;
Fig. 3 is the angle change curve schematic diagram of sample point of the present invention;
Fig. 4 utilizes the present invention from Fig. 3, to extract the schematic diagram of flex point;
Fig. 5 utilizes the present invention from Fig. 3, to extract the schematic diagram of unique point;
Fig. 6 be of the present invention to unique point travel direction vector coding to obtain the detail flowchart of the step of direction vector sequence;
Fig. 7 is direction vector coding schematic diagram of the present invention;
Fig. 8 utilizes the schematic diagram of Fig. 7 to one group of random character point travel direction vector coding;
Fig. 9 is the detail flowchart that identifies the step of the symbol corresponding with gesture of the present invention;
Figure 10 is the structural drawing of the gesture recognition system of touch screen terminal provided by the invention;
Figure 11 is the structural drawing of characteristic extracting module in Figure 10;
Figure 12 is the structural drawing of direction vector coding module in Figure 10;
Figure 13 is the structural drawing of matching module in Figure 10.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
In order to solve, existingly based on optical means, realize the problem that gesture identification mode exists, the present invention proposes a kind of gesture identification method of touch screen terminal, the method is to gather the series of features point in gesture by touch-screen, by to unique point travel direction vector coding, and coding result is mated with reference template, thereby obtain the symbol corresponding with gesture.
Fig. 1 shows the flow process of the gesture identification method of touch screen terminal provided by the invention, comprising:
Step S1: obtain the coordinate point sequence of gesture by touch-screen, and coordinate point sequence is carried out to filtering processing.
Because shake easily appears in the hand-written data on touch-screen, thereby in the present invention, after getting coordinate point sequence, need to carry out the disposal of gentle filter to coordinate point sequence.Preferably, adopt weighted filtering algorithm to carry out filtering processing to coordinate point sequence.
For instance, suppose that the coordinate point sequence getting is: S=u 1u 2u l, wherein, u l=(x l, y l), 1≤l≤L, u 1the starting point coordinate in coordinate point sequence, u lbe the terminal point coordinate in coordinate point sequence, L is that the coordinate in coordinate point sequence is counted, and the process that adopts weighted filtering algorithm to carry out filtering processing to coordinate point sequence can be expressed as:
p j = 1 W Σ i = j - k j + k ω i u i ,
Wherein,
Figure BDA0000441160260000042
k is that the window of glide filter is long, ω ifor the weight in different coordinate points, p jfor filtered coordinate points.For convenience of realizing, the long k=2 of desirable window, weighting value is pascal's triangle coefficient, i.e. ω=Isosorbide-5-Nitrae, 6,4,1, have:
p j = 1 16 ( u i - 2 + 4 u i - 1 + 6 u i + 4 u i + 1 + u i + 2 )
Thereby the coordinate point sequence obtaining after filtering is processed is: S '=p 1p 2p l.
Step S2: extract minutiae in the coordinate point sequence from filtering is processed.
In the present invention, unique point refers to some coordinate points of the skeleton structure that can reflect the represented symbol of gesture.General, the different coordinate points in stroke have different curvature information, and unique point all has maximum angular velocity conventionally, and based on this, further, as shown in Figure 2, step S2 can comprise:
Step S21: in the coordinate point sequence after calculation of filtered is processed, the line segment between adjacent two coordinate points and the angle between horizontal line, obtain angle sequence.
Step S22: angle sequence is carried out to low-pass filtering treatment, so that angle sequence is more level and smooth.
Step S23: the angle sequence after low-pass filtering treatment is carried out to difference processing, obtain difference value sequence.
Step S24: recognition differential divides in value sequence, is greater than the difference value of threshold value, and determines the flex point in coordinate point sequence according to recognition result.
Step S25: the intermediate point between the starting point in coordinate point sequence, terminal, flex point and adjacent flex point goes out as feature point extraction.
For instance, any two the coordinate points p in false coordinate point sequence l-1, p lbetween the line segment that forms and the angle between horizontal line be made as a l, the angle sequence obtaining after step S21 is: A=a 1a 2a l-1.Afterwards, by step S22, angle sequence A is carried out to low-pass filtering treatment.Afterwards, in step S23, filtered angle sequence A is carried out to difference processing, its objective is in order to draw the angle changing value between adjacent angle in angle sequence, as shown in Figure 3; Suppose that difference value is Δ A, this step can be expressed as: Δ A=diff (A), wherein, diff () represents the difference processing to angle sequence.Afterwards, in step S24, by the comparison to each difference value Δ A and threshold value in difference value sequence, show that angle changes maximum coordinate points, both can be defined as flex point, as shown in the coordinate points representing with circle in Fig. 4.Afterwards, in step S25, retain the intermediate point between adjacent flex point, and using starting point, terminal, flex point and intermediate point jointly as the unique point of gesture, as shown in the coordinate points representing with circle in Fig. 5.
Step S3: to unique point travel direction vector coding, obtain direction vector sequence.
Further, as shown in Figure 6, step S3 can comprise:
Step S31: calculate horizontal ordinate difference and ordinate difference between adjacent feature point, and by horizontal ordinate difference and ordinate difference respectively with direction value representation.
For instance, if horizontal ordinate difference is to be greater than 0 positive number, can stipulate that its direction value is 1, if horizontal ordinate difference is to be less than 0 negative, can stipulate that its direction value is-1, if horizontal ordinate difference is 0, can stipulate that its direction value is 0; If ordinate difference is to be greater than 0 positive number, can stipulate that its direction value is 1, if ordinate difference is to be less than 0 negative, can stipulate that its direction value is-1, if ordinate difference is 0, can stipulate that its direction value is 0.
Step S32: in search direction vector definition list, the direction vector value corresponding with the direction value of every pair of adjacent feature point, all directions vector value forms direction vector sequence, and this direction vector sequence is the coding result obtaining after direction vector coding.
Wherein, direction vector sequence D can be expressed as: D=d 1d 2d l-1, d ldenotation coordination point p l-1with coordinate points p lbetween direction vector, and d l∈ { 0,1,2,3,4,5,6,7}, 1≤l≤L-1.In the present invention, d lvalue can, by the magnitude relationship between coordinate points, by vector definition list, obtain.
Wherein, vector definition list has characterized the corresponding relation between direction vector value and the direction value of coordinate points.For instance, typical direction vector value comprises 8 directions as shown in 0-7 in Fig. 7, and direction vector definition list can be as shown in following table one:
Table one
d l 0 1 2 3 4 5 6 7
ΔX 1 1 0 -1 -1 -1 0 1
ΔY 0 1 1 1 0 -1 -1 -1
In table one, Δ X is the horizontal ordinate difference with direction value representation, and Δ Y is the ordinate difference with direction value representation., by step S31, horizontal ordinate difference and ordinate difference being expressed as after direction value, by look-up table one, can obtain every pair of adjacent feature and put corresponding direction vector value, all directions vector value has formed direction vector sequence jointly.For example, if the unique point extracting through step S2 distributes as shown in Figure 8,, after execution step S31, by look-up table one, the direction vector sequence after can being encoded is 43221007.
Step S4: direction vector sequence is mated with reference template, to identify the symbol corresponding with gesture.
Further, as shown in Figure 9, step S4 can comprise:
Step S41: utilize dynamic programming algorithm, the maximum similarity in calculated direction vector sequence and reference template between the direction vector sequence of each symbol.Wherein, reference template has characterized the corresponding relation between symbol and direction vector sequence.
In the present invention, similarity is defined as follows shown in table two:
Table two
d l 0 1 2 3 4 5 6 7
0 10 6 0 0 0 0 0 6
1 6 10 6 0 0 0 0 0
2 0 6 10 6 0 0 0 0
3 0 0 6 10 6 0 0 0
4 0 0 0 6 10 6 0 0
5 0 0 0 0 6 10 6 0
6 0 0 0 0 0 6 10 6
7 6 0 0 0 0 0 6 10
If the symbol C that gesture is corresponding idirection vector sequence be D i, character C in the reference template comparing with it rdirection vector sequence be D r, have: D i=d i1d i2d iM-1, D r=d r1d r2d rN-1.Utilize dynamic programming algorithm, can calculate direction vector sequence D iwith direction vector sequence be D rbetween maximum similarity S (D i, D r).
Step S42: if maximum similarity S is (D i, D r) be greater than threshold value threshold, that is: S (D i, D r) >threshold, select character that maximum similarity is corresponding as the symbol corresponding with gesture.
Afterwards, by step S4, obtaining after symbol corresponding to gesture, the present invention also can comprise:
Step S5: wake the application program corresponding with the symbol identifying up, or carry out the operation corresponding with the symbol identifying.
Figure 10 shows the structure of the gesture recognition system of touch screen terminal provided by the invention, for convenience of explanation, only shows part related to the present invention.
The gesture recognition system of touch screen terminal provided by the invention comprises: pretreatment module 1, for obtain the coordinate point sequence of gesture by touch-screen, and coordinate point sequence is carried out to filtering processing; Characteristic extracting module 2, for the coordinate point sequence extract minutiae from pretreatment module 1 filtering is processed; Direction vector coding module 3, the unique point travel direction vector coding for characteristic extracting module 2 is extracted, obtains direction vector sequence; Matching module 4, mates with reference template for the direction vector sequence that direction vector coding module 3 is obtained, to identify the symbol corresponding with gesture.
The gesture recognition system of touch screen terminal provided by the invention also can comprise: execution module 5, and for waking application program corresponding to symbol identifying with matching module 4 up, or operation corresponding to symbol that identify with matching module 4 of execution.
Figure 11 shows the structure of characteristic extracting module 2 in Figure 10.
Particularly, characteristic extracting module 2 can comprise: the first calculating sub module 21, for calculating coordinate point sequence after pretreatment module 1 filtering is processed, line segment between adjacent two coordinate points and the angle between horizontal line, obtains angle sequence; Filtering submodule 22, carries out low-pass filtering treatment for the angle sequence that the first calculating sub module 21 is obtained, so that angle sequence is more level and smooth; Difference subspace module 23, for the angle sequence after filtering submodule 22 low-pass filtering treatment is carried out to difference processing, obtains difference value sequence; Recognin module 24, divides the difference value sequence that submodule 23 obtains, the difference value that is greater than threshold value for recognition differential, and determines the flex point in coordinate point sequence according to recognition result; Extract submodule 25, for the definite flex point of the starting point of coordinate point sequence, terminal, recognin module 24 and the intermediate point between adjacent flex point are gone out as feature point extraction.
Figure 12 shows the structure of direction vector coding module 3 in Figure 10.
Particularly, direction vector coding module 3 can comprise: the second calculating sub module 31, for calculating horizontal ordinate difference and the ordinate difference between adjacent feature point, and by horizontal ordinate difference and ordinate difference respectively with direction value representation; Search submodule 32, for search direction vector definition list, the direction vector value corresponding with the direction value of every pair of adjacent feature point, all directions vector value forms direction vector sequence, and this direction vector sequence is the coding result obtaining after direction vector coding.
Figure 13 shows the structure of matching module 4 in Figure 10.
Particularly, matching module 4 can comprise: the 3rd calculating sub module 41, be used for utilizing dynamic programming algorithm, the maximum similarity in calculated direction vector sequence and reference template between the direction vector sequence of each symbol, this reference template has characterized the corresponding relation between symbol and direction vector sequence; Chooser module 42, while being greater than threshold value for the maximum similarity calculating when the 3rd calculating sub module 41, selects character that maximum similarity is corresponding as the symbol corresponding with gesture.
In addition, the present invention also provides a kind of touch screen terminal, comprises the gesture recognition system of a touch screen terminal as above, is not repeated herein.
Gesture identification method and the system of the touch screen terminal that the present invention proposes are to gather the series of features point in gesture by touch-screen, by to unique point travel direction vector coding, and coding result is mated with reference template, thereby obtain the symbol corresponding with gesture, can effectively identify the formed symbol of user's gesture slip touch-screen.With respect to prior art, this recognition method realizes simple, user-friendly, and without camera support, can reduce and realize cost, and is not subject to the impact of ambient light or touch screen terminal mobile status, and discrimination is high.In addition, after identifying symbol, can utilize recognition result waken system call corresponding application program under the dark set of hanging scrolls part of touch-screen, such as calling conventional call function etc., thereby avoided the frequent use of touch screen terminal power source key, reduce and start the required step of application program, handled easily, and the serviceable life of having improved touch screen terminal; Meanwhile, due under dark set of hanging scrolls part, for guaranteeing low power consumption, the data volume adopting is limited, and therefore, the present invention adopts the mode of extracting less unique point, the symbol skeleton that utilizes unique point to form is realized Symbol recognition, is specially adapted to the efficient gesture identification under low power consumption.Certainly, in practice, also can utilize the symbol identifying carry out other operation or derive more application, at this, not enumerate.
One of ordinary skill in the art will appreciate that all or part of step realizing in above-described embodiment method is can control relevant hardware by program to complete, described program can be in being stored in a computer read/write memory medium, described storage medium, as ROM/RAM, disk, CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.

Claims (10)

1. a gesture identification method for touch screen terminal, is characterized in that, said method comprising the steps of:
By touch-screen, obtain the coordinate point sequence of gesture, and coordinate point sequence is carried out to filtering processing;
Extract minutiae in described coordinate point sequence from filtering is processed;
To described unique point travel direction vector coding, obtain direction vector sequence;
Described direction vector sequence is mated with reference template, and to identify the symbol corresponding with described gesture, described reference template has characterized the corresponding relation between symbol and direction vector sequence.
2. the gesture identification method of touch screen terminal as claimed in claim 1, it is characterized in that, described, described direction vector sequence is mated with reference template, after identifying the step of the symbol corresponding with described gesture, described method is further comprising the steps of:
Wake the application program corresponding with the described symbol identifying up, or carry out the operation corresponding with the described symbol identifying.
3. the gesture identification method of touch screen terminal as claimed in claim 1 or 2, is characterized in that, in described described coordinate point sequence from filtering is processed, the step of extract minutiae comprises the following steps:
In described coordinate point sequence after calculation of filtered is processed, the line segment between adjacent two coordinate points and the angle between horizontal line, obtain angle sequence;
Described angle sequence is carried out to low-pass filtering treatment;
Described angle sequence after low-pass filtering treatment is carried out to difference processing, obtain difference value sequence;
Identify in described difference value sequence, be greater than the difference value of threshold value, and determine the flex point in described coordinate point sequence according to recognition result;
Intermediate point between the starting point in described coordinate point sequence, terminal, described flex point and adjacent flex point goes out as feature point extraction.
4. the gesture identification method of touch screen terminal as claimed in claim 1 or 2, is characterized in that, described to described unique point travel direction vector coding, the step that obtains direction vector sequence comprises the following steps:
Calculate horizontal ordinate difference and ordinate difference between adjacent feature point, and by described horizontal ordinate difference and described ordinate difference respectively with direction value representation;
In search direction vector definition list, the direction vector value corresponding with the described direction value of every pair of adjacent feature point, described in each, direction vector value forms direction vector sequence.
5. the gesture identification method of touch screen terminal as claimed in claim 1 or 2, is characterized in that, described described direction vector sequence is mated with reference template, to identify the step of the symbol corresponding with described gesture, comprises the following steps:
Utilize dynamic programming algorithm, calculate the maximum similarity between the direction vector sequence of each symbol in described direction vector sequence and reference template;
If described maximum similarity is greater than threshold value, select character that described maximum similarity is corresponding as the symbol corresponding with described gesture.
6. a gesture recognition system for touch screen terminal, is characterized in that, described system comprises:
Pretreatment module, for obtain the coordinate point sequence of gesture by touch-screen, and carries out filtering processing to described coordinate point sequence;
Characteristic extracting module, for the described coordinate point sequence extract minutiae from described pretreatment module filtering is processed;
Direction vector coding module, the described unique point travel direction vector coding for described characteristic extracting module is extracted, obtains direction vector sequence;
Matching module, mates with reference template for the described direction vector sequence that described direction vector coding module is obtained, and to identify the symbol corresponding with gesture, described reference template has characterized the corresponding relation between symbol and direction vector sequence.
7. the gesture recognition system of touch screen terminal as claimed in claim 6, is characterized in that, described system also comprises:
Execution module, for waking application program corresponding to described symbol identifying with described matching module up, or operation corresponding to described symbol that identify with described matching module of execution.
8. the gesture recognition system of touch screen terminal as claimed in claim 6, is characterized in that, described characteristic extracting module comprises:
The first calculating sub module, for calculating described coordinate point sequence after described pretreatment module filtering is processed, line segment between adjacent two coordinate points and the angle between horizontal line, obtains angle sequence;
Filtering submodule, carries out low-pass filtering treatment for the described angle sequence that described the first calculating sub module is obtained;
Difference subspace module, for the described angle sequence after described filtering submodule low-pass filtering treatment is carried out to difference processing, obtains difference value sequence;
Recognin module, for identifying the described difference value sequence that described difference subspace module obtains, the difference value that is greater than threshold value, and determines the flex point in described coordinate point sequence according to recognition result;
Extract submodule, for described flex point that the starting point of described coordinate point sequence, terminal, described recognin module are determined and the intermediate point between adjacent flex point, as feature point extraction, go out.
9. the gesture recognition system of touch screen terminal as claimed in claim 6, is characterized in that, described matching module comprises:
The 3rd calculating sub module, for utilizing dynamic programming algorithm, calculates the maximum similarity between the direction vector sequence of each symbol in described direction vector sequence and described reference template;
Chooser module, while being greater than threshold value for the described maximum similarity calculating when described the 3rd calculating sub module, selects character that described maximum similarity is corresponding as the symbol corresponding with described gesture.
10. a touch screen terminal, comprises touch-screen, it is characterized in that, described touch screen terminal also comprises the gesture recognition system of touch screen terminal, and described system is the gesture recognition system of the touch screen terminal as described in claim 6 to 9 any one.
CN201310700794.8A 2013-12-19 2013-12-19 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal Pending CN103677642A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201310700794.8A CN103677642A (en) 2013-12-19 2013-12-19 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal
PCT/CN2014/084146 WO2015090075A1 (en) 2013-12-19 2014-08-12 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310700794.8A CN103677642A (en) 2013-12-19 2013-12-19 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal

Publications (1)

Publication Number Publication Date
CN103677642A true CN103677642A (en) 2014-03-26

Family

ID=50315357

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310700794.8A Pending CN103677642A (en) 2013-12-19 2013-12-19 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal

Country Status (2)

Country Link
CN (1) CN103677642A (en)
WO (1) WO2015090075A1 (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103995665A (en) * 2014-04-14 2014-08-20 深圳市汇顶科技股份有限公司 Mobile terminal and method and system for getting access to application programs in ready mode
CN104460999A (en) * 2014-11-28 2015-03-25 广东欧珀移动通信有限公司 Method and device for recognizing gesture with inflection point
WO2015090075A1 (en) * 2013-12-19 2015-06-25 深圳市汇顶科技股份有限公司 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal
CN105138115A (en) * 2015-07-28 2015-12-09 Tcl移动通信科技（宁波）有限公司 Touch screen based mobile terminal awakening method and system
WO2017092296A1 (en) * 2015-12-03 2017-06-08 深圳市汇顶科技股份有限公司 Gesture unlocking method and apparatus, and mobile terminal
CN110109551A (en) * 2019-05-17 2019-08-09 中国科学院电子学研究所 Gesture identification method, device, equipment and storage medium
WO2020000673A1 (en) * 2018-06-27 2020-01-02 青岛清原精准农业科技有限公司 Method for drawing chemical structural formula based on recognition of gestures in dynamic gesture library
CN111459395A (en) * 2020-03-30 2020-07-28 北京集创北方科技股份有限公司 Gesture recognition method and system, storage medium and man-machine interaction device
CN112947836A (en) * 2019-12-11 2021-06-11 北京集创北方科技股份有限公司 Gesture recognition method and system based on inflection point characteristics, storage medium and touch screen device
CN113093972A (en) * 2019-12-23 2021-07-09 北京集创北方科技股份有限公司 Gesture recognition method and system, storage medium and touch screen device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0612493A (en) * 1992-06-25 1994-01-21 Hitachi Ltd Gesture recognizing method and user interface method
US5347477A (en) * 1992-01-28 1994-09-13 Jack Lee Pen-based form computer
CN101339487A (en) * 2008-08-29 2009-01-07 飞图科技（北京）有限公司 Method for recognizing funcall by shortcut pattern based on hand-held equipment
CN102298486A (en) * 2010-06-22 2011-12-28 广东国笔科技股份有限公司 Fast calling system and method based on touch screen
CN103034429A (en) * 2011-10-10 2013-04-10 北京千橡网景科技发展有限公司 Identity authentication method and device for touch screen
CN103442114A (en) * 2013-08-16 2013-12-11 中南大学 Identity authentication method based on dynamic gesture

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7821503B2 (en) * 2003-04-09 2010-10-26 Tegic Communications, Inc. Touch screen and graphical user interface
CN103455265B (en) * 2012-06-01 2015-12-09 腾讯科技（深圳）有限公司 The control method of controlled plant and system, mobile terminal and controlled plant
US20140053113A1 (en) * 2012-08-15 2014-02-20 Prss Holding BV Processing user input pertaining to content movement
CN103677642A (en) * 2013-12-19 2014-03-26 深圳市汇顶科技股份有限公司 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5347477A (en) * 1992-01-28 1994-09-13 Jack Lee Pen-based form computer
JPH0612493A (en) * 1992-06-25 1994-01-21 Hitachi Ltd Gesture recognizing method and user interface method
CN101339487A (en) * 2008-08-29 2009-01-07 飞图科技（北京）有限公司 Method for recognizing funcall by shortcut pattern based on hand-held equipment
CN102298486A (en) * 2010-06-22 2011-12-28 广东国笔科技股份有限公司 Fast calling system and method based on touch screen
CN103034429A (en) * 2011-10-10 2013-04-10 北京千橡网景科技发展有限公司 Identity authentication method and device for touch screen
CN103442114A (en) * 2013-08-16 2013-12-11 中南大学 Identity authentication method based on dynamic gesture

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
周航慈: "《嵌入式系统软件设计中的常用算法》", 31 January 2010, 北京航空航天大学出版社 *
多模态人机交互中基于笔输入的手势识别;王延江;《北方交通大学学报》;20010430;第25卷(第2期);第10-13页，图1，图2，图4，图7 *
旋转方向无关的无约束手写中文词组识别;龙腾;《中国博士学位论文全文数据库 信息科技辑》;20081115(第11期);I138-31-第18页，第31页 *
王延江: "多模态人机交互中基于笔输入的手势识别", 《北方交通大学学报》 *
龙腾: "旋转方向无关的无约束手写中文词组识别", 《中国博士学位论文全文数据库 信息科技辑》 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015090075A1 (en) * 2013-12-19 2015-06-25 深圳市汇顶科技股份有限公司 Touch screen terminal and method and system for identifying hand gestures of touch screen terminal
CN103995665A (en) * 2014-04-14 2014-08-20 深圳市汇顶科技股份有限公司 Mobile terminal and method and system for getting access to application programs in ready mode
CN104460999A (en) * 2014-11-28 2015-03-25 广东欧珀移动通信有限公司 Method and device for recognizing gesture with inflection point
CN104460999B (en) * 2014-11-28 2017-07-28 广东欧珀移动通信有限公司 A kind of gesture identification method and device with flex point
CN105138115A (en) * 2015-07-28 2015-12-09 Tcl移动通信科技（宁波）有限公司 Touch screen based mobile terminal awakening method and system
WO2017092296A1 (en) * 2015-12-03 2017-06-08 深圳市汇顶科技股份有限公司 Gesture unlocking method and apparatus, and mobile terminal
WO2020000673A1 (en) * 2018-06-27 2020-01-02 青岛清原精准农业科技有限公司 Method for drawing chemical structural formula based on recognition of gestures in dynamic gesture library
CN110109551A (en) * 2019-05-17 2019-08-09 中国科学院电子学研究所 Gesture identification method, device, equipment and storage medium
CN112947836A (en) * 2019-12-11 2021-06-11 北京集创北方科技股份有限公司 Gesture recognition method and system based on inflection point characteristics, storage medium and touch screen device
CN113093972A (en) * 2019-12-23 2021-07-09 北京集创北方科技股份有限公司 Gesture recognition method and system, storage medium and touch screen device
CN111459395A (en) * 2020-03-30 2020-07-28 北京集创北方科技股份有限公司 Gesture recognition method and system, storage medium and man-machine interaction device

Also Published As

Publication number Publication date
WO2015090075A1 (en) 2015-06-25

Similar Documents

Publication Publication Date Title
CN103677642A (en) Touch screen terminal and method and system for identifying hand gestures of touch screen terminal
RU2711029C2 (en) Touch classification
CN109614922B (en) Dynamic and static gesture recognition method and system
Duan et al. An improved Hough transform for line detection
WO2017092296A1 (en) Gesture unlocking method and apparatus, and mobile terminal
CN103399896B (en) The method and system of incidence relation between identification user
WO2015158116A1 (en) Mobile terminal, and implementation method and system for same to enter application program in standby state
US20130050076A1 (en) Method of recognizing a control command based on finger motion and mobile device using the same
Premaratne et al. Centroid tracking based dynamic hand gesture recognition using discrete Hidden Markov Models
CN104123007A (en) Multidimensional weighted 3D recognition method for dynamic gestures
US20100329562A1 (en) Statistical Online Character Recognition
CN110308795B (en) Dynamic gesture recognition method and system
CN101611417A (en) The method that is used for character recognition
CN105844216A (en) Detection and matching mechanism for recognition of handwritten letters using WiFi signals
CN107315995B (en) Face recognition method based on Laplace logarithmic face and convolutional neural network
CN103473492A (en) Method and user terminal for recognizing permission
CN102929394B (en) A kind of Braille input method based on gesture identification
CN103472915A (en) Reading control method and reading control device on basis of pupil tracking and display equipment
CN111492407B (en) System and method for map beautification
CN106023184A (en) Depth significance detection method based on anisotropy center-surround difference
CN112633420A (en) Image similarity determination and model training method, device, equipment and medium
CN102306060B (en) Input method and system of mobile equipment
CN106201314A (en) A kind of display packing realizing handwriting input on touch screen and display device
CN114898376A (en) Formula identification method, device, equipment and medium
CN114373212A (en) Face recognition model construction method, face recognition method and related equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20140326

RJ01 Rejection of invention patent application after publication